Skip to content

Commit e983311

Browse files
committed
2025_04 - Fix monthly broken links - jboback
1 parent dcacc45 commit e983311

File tree

1 file changed

+2
-2
lines changed
  • articles/ai-services/language-service/question-answering/includes

1 file changed

+2
-2
lines changed

articles/ai-services/language-service/question-answering/includes/sdk-python.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -112,7 +112,7 @@ Confidence Score: 0.9185
112112

113113
The confidence score returns a value between 0 and 1. You can think of this like a percentage and multiply by 100 so a confidence score of 0.9185 means custom question answering is 91.85% confident this is the correct answer to the question based on the project.
114114

115-
If you want to exclude answers where the confidence score falls below a certain threshold, you can modify the [AnswerOptions](https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-language-questionanswering/1.0.0/azure.ai.language.questionanswering.models.html#azure.ai.language.questionanswering.models.AnswersOptions) to add the `confidence_threshold` parameter.
115+
If you want to exclude answers where the confidence score falls below a certain threshold, you can modify the AnswerOptions to add the `confidence_threshold` parameter.
116116

117117
```python
118118
output = client.get_answers(
@@ -182,5 +182,5 @@ A: Power and charging. It takes two to four hours to charge the Surface Pro 4 ba
182182
Confidence Score: 0.9254655838012695
183183
```
184184

185-
In this case, we iterate through all responses and only return the response with the highest confidence score that is greater than 0.9. To understand more about the options available with get_answers_from_text, review the [AnswersFromTextOptions parameters](https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-language-questionanswering/1.0.0/azure.ai.language.questionanswering.models.html#azure.ai.language.questionanswering.models.AnswersFromTextOptions).
185+
In this case, we iterate through all responses and only return the response with the highest confidence score that is greater than 0.9. To understand more about the options available with get_answers_from_text, review the AnswersFromTextOptions parameters.
186186

0 commit comments

Comments
 (0)